© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128872
    Prev
    Next
    INDEX
    Explanations

    code declaration blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     other
    -1.19
     AssemblyVersion
    -1.00
    此外
    -0.93
    other
    -0.93
     OTHER
    -0.90
    mentet
    -0.89
    ::$_
    -0.89
    が登場
    -0.89
    がありますが
    -0.88
    ferential
    -0.88
    POSITIVE LOGITS
     its
    1.01
     его
    0.94
     suoi
    0.93
    土産
    0.90
    其
    0.90
     mobiliario
    0.89
     klachten
    0.88
     bedeutend
    0.88
     solltest
    0.88
    ..-
    0.86
    Activations Density 0.008%

    No Known Activations